|
MultiSource/Benchmarks/MiBench/automotive-bitcount/automotive-bitcount
Profile
|
39.78% |
0.071 |
0.099 |
0.000 |
-0.07% |
0.000 |
|
MultiSource/Benchmarks/Trimaran/enc-pc1/enc-pc1
Profile
|
37.77% |
0.461 |
0.636 |
0.000 |
11.26% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/5001
|
33.31% |
10.731 |
14.305 |
0.000 |
16.85% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/171
|
32.31% |
0.374 |
0.495 |
0.006 |
32.06% |
0.006 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/999
|
27.13% |
866.887 |
1102.042 |
0.037 |
27.53% |
0.037 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/999
|
27.08% |
1707.493 |
2169.950 |
4.828 |
28.04% |
4.828 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC1
|
26.56% |
5.083 |
6.433 |
0.000 |
12.50% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/51
|
23.64% |
105.785 |
130.793 |
0.001 |
22.81% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/51
|
23.33% |
64.328 |
79.333 |
0.001 |
24.70% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/171
|
23.31% |
0.303 |
0.373 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/256
|
23.27% |
248.724 |
306.613 |
0.009 |
24.69% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/256
|
23.21% |
468.135 |
576.774 |
0.023 |
26.68% |
0.023 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<1, EqZero, First>
|
23.19% |
11887.525 |
14644.174 |
0.598 |
23.08% |
0.598 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/28
|
21.87% |
45.744 |
55.747 |
0.002 |
21.86% |
0.002 |
|
External/SPEC/CINT2017rate/525.x264_r/525.x264_r
Profile
|
21.47% |
102.279 |
124.242 |
0.038 |
1.35% |
0.038 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC2
|
20.00% |
7.147 |
8.577 |
0.000 |
19.81% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/28
|
20.00% |
67.899 |
81.475 |
0.003 |
19.98% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC2
|
19.99% |
7.147 |
8.576 |
0.000 |
19.93% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW8From_uint16_t_To_uint8_t_
|
19.95% |
11928.733 |
14308.741 |
2.626 |
19.93% |
2.626 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint8_t_
|
19.91% |
11935.197 |
14311.280 |
1.535 |
19.97% |
1.535 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint8_t_To_uint32_t_
|
19.90% |
11928.596 |
14301.978 |
0.224 |
19.84% |
0.224 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint32_t_
|
19.89% |
11928.464 |
14301.453 |
0.308 |
19.78% |
0.308 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopFrom_uint16_t_To_uint8_t_
|
19.79% |
11938.740 |
14301.706 |
4.688 |
19.87% |
4.688 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecInLoopWithVW16From_uint16_t_To_uint32_t_
|
19.78% |
11939.910 |
14301.835 |
5.972 |
19.84% |
5.972 |
|
SingleSource/Benchmarks/Shootout-C++/Shootout-C++-matrix
Profile
|
18.50% |
5.561 |
6.589 |
0.100 |
-0.01% |
0.100 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_autovec_int64_t_
|
17.51% |
680031.128 |
799131.429 |
1537.956 |
0.03% |
1537.956 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/512
|
17.21% |
17199.300 |
20158.657 |
21.967 |
-0.03% |
21.967 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_only_autovec_int64_t_
|
17.05% |
677754.114 |
793300.795 |
1209.602 |
-0.04% |
1209.602 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint16_t>/65
|
16.43% |
82.915 |
96.541 |
0.627 |
16.43% |
0.627 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/16
|
16.41% |
47.887 |
55.747 |
0.002 |
16.40% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/16
|
16.27% |
30.736 |
35.735 |
0.001 |
13.63% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/128
|
16.02% |
928.770 |
1077.593 |
0.094 |
-0.06% |
0.094 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/256
|
15.76% |
3956.288 |
4579.882 |
7.009 |
-0.05% |
7.009 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/16
|
15.37% |
37.169 |
42.883 |
0.001 |
15.27% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/5001
|
14.84% |
10.731 |
12.323 |
0.000 |
-0.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC64
|
14.66% |
64.118 |
73.520 |
0.774 |
14.28% |
0.774 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_boxBlurKernel/1024
|
14.66% |
73811.778 |
84629.250 |
100.925 |
-0.14% |
100.925 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int32_t_
|
14.36% |
521382.707 |
596262.887 |
1806.670 |
5.71% |
1806.670 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint8_t>/10
|
13.21% |
37.880 |
42.884 |
0.001 |
13.19% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_csa_with_cond_arith_novec_int64_t_
|
13.05% |
692989.109 |
783393.498 |
1312.453 |
13.39% |
1312.453 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/28
|
12.72% |
39.312 |
44.313 |
0.002 |
10.70% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-md5/enc-md5
Profile
|
12.04% |
2.685 |
3.009 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/65
|
11.93% |
143.673 |
160.817 |
0.003 |
11.38% |
0.003 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIND_FIRST_MIN_LAMBDA/44217
|
11.80% |
118.005 |
131.927 |
0.551 |
6.42% |
0.551 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/256
|
11.31% |
993.254 |
1105.583 |
0.174 |
-0.01% |
0.174 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/512
|
10.89% |
3990.537 |
4425.120 |
17.958 |
-0.21% |
17.958 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchAutoVec<uint16_t>/127
|
10.87% |
269.476 |
298.778 |
8.289 |
10.57% |
8.289 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint8_t>/10
|
10.86% |
32.879 |
36.450 |
0.001 |
10.86% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC2
|
10.00% |
7.147 |
7.862 |
0.000 |
-8.33% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/171
|
9.90% |
0.376 |
0.413 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, First>
|
9.59% |
2280.828 |
2499.450 |
0.013 |
9.00% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC4
|
9.09% |
7.862 |
8.577 |
0.000 |
9.09% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC4
|
9.08% |
7.862 |
8.577 |
0.000 |
9.08% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/51
|
9.08% |
55.038 |
60.036 |
0.002 |
7.69% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Dither/Dither.test:BENCHMARK_FLOYD_DITHER/128
|
9.05% |
251.143 |
273.867 |
0.374 |
0.04% |
0.374 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC4
|
9.03% |
7.867 |
8.577 |
0.000 |
-20.00% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_HYDRO_1D_LAMBDA/171
|
8.78% |
0.456 |
0.496 |
0.000 |
8.77% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, GreaterThanZero, First>
|
8.71% |
4496.121 |
4887.583 |
6.088 |
8.68% |
6.088 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/5001
|
8.62% |
10.010 |
10.874 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC128
|
8.54% |
141.574 |
153.670 |
0.003 |
1.80% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/10
|
8.50% |
33.594 |
36.451 |
0.001 |
6.24% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_single_csa_cond_load_novec_int64_t_
|
8.10% |
798111.872 |
862734.568 |
1266.558 |
7.54% |
1266.558 |
|
External/SPEC/CFP2017rate/508.namd_r/508.namd_r
Profile
|
7.93% |
77.624 |
83.778 |
0.075 |
-0.28% |
0.075 |
|
SingleSource/Benchmarks/McGill/misr
Profile
|
7.73% |
0.410 |
0.442 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/128
|
7.52% |
3341.708 |
3593.077 |
0.393 |
-0.03% |
0.393 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_ENERGY_CALC_RAW/44217
|
7.35% |
2133.770 |
2290.595 |
27.696 |
0.08% |
27.696 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint32_t>/10
|
7.31% |
29.305 |
31.448 |
0.001 |
9.99% |
0.001 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/256
|
7.22% |
14311.082 |
15344.891 |
1.938 |
-0.03% |
1.938 |
|
SingleSource/Benchmarks/Shootout/Shootout-lists
Profile
|
7.17% |
9.640 |
10.331 |
0.004 |
-0.04% |
0.004 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC7
|
7.14% |
10.006 |
10.721 |
0.000 |
7.14% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC7
|
7.14% |
10.007 |
10.721 |
0.000 |
7.14% |
0.000 |
|
MultiSource/Applications/JM/lencod/lencod
Profile
|
6.71% |
13.701 |
14.621 |
0.019 |
0.77% |
0.019 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForLoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchAutoVecForBigLoopTC1
|
6.66% |
5.361 |
5.718 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC31
|
6.55% |
148.909 |
158.669 |
0.003 |
5.97% |
0.003 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/512
|
6.53% |
59575.500 |
63468.364 |
88.896 |
-0.03% |
88.896 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC32
|
6.35% |
153.899 |
163.676 |
0.002 |
6.76% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4LoopTC4
|
6.25% |
11.436 |
12.151 |
0.000 |
6.24% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC128
|
6.06% |
614.558 |
651.829 |
0.042 |
5.36% |
0.042 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_FIND_FIRST_MIN_RAW/44217
|
6.05% |
119.382 |
126.610 |
0.823 |
-0.56% |
0.823 |
|
SingleSource/Benchmarks/Adobe-C++/loop_unroll
Profile
|
5.95% |
1.618 |
1.715 |
0.001 |
0.03% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC64
|
5.94% |
305.614 |
323.777 |
0.002 |
5.40% |
0.002 |
|
MultiSource/Benchmarks/Trimaran/enc-rc4/enc-rc4
Profile
|
5.94% |
1.825 |
1.933 |
0.003 |
-0.10% |
0.003 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_add_xor_no_runtime_checks_needed<16, int>
|
5.76% |
37.167 |
39.308 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, None>
|
5.72% |
20496.603 |
21668.431 |
15.231 |
2.78% |
15.231 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC127
|
5.52% |
614.354 |
648.265 |
0.020 |
5.37% |
0.020 |
|
MicroBenchmarks/SLPVectorization/SLPVectorizationBenchmarks.test:benchmark_xor_no_runtime_checks_needed<16, int>
|
5.40% |
26.445 |
27.874 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC15
|
5.40% |
136.522 |
143.890 |
0.181 |
1.90% |
0.181 |
|
MicroBenchmarks/LCALS/SubsetCLambdaLoops/lcalsCLambda.test:BM_FIRST_DIFF_LAMBDA/44217
|
5.38% |
91.175 |
96.080 |
0.039 |
0.01% |
0.039 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC31
|
5.28% |
274.061 |
288.541 |
0.018 |
0.09% |
0.018 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC31
|
5.26% |
274.041 |
288.460 |
0.041 |
0.10% |
0.041 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC31
|
5.21% |
274.086 |
288.355 |
0.012 |
0.01% |
0.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC8
|
5.16% |
41.459 |
43.599 |
0.001 |
5.05% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC128
|
5.16% |
1131.444 |
1189.811 |
0.013 |
-0.19% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC64
|
5.13% |
566.774 |
595.872 |
0.087 |
0.03% |
0.087 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC64
|
5.13% |
566.762 |
595.811 |
0.048 |
0.01% |
0.048 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC128
|
5.10% |
1132.055 |
1189.823 |
0.209 |
0.05% |
0.209 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC15
|
5.09% |
136.524 |
143.478 |
0.046 |
0.33% |
0.046 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/16
|
5.08% |
42.171 |
44.314 |
0.001 |
3.33% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC63
|
5.08% |
559.341 |
587.762 |
0.023 |
0.08% |
0.023 |
|
MultiSource/Benchmarks/VersaBench/ecbdes/ecbdes
Profile
|
5.08% |
3.829 |
4.023 |
0.000 |
-0.02% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC63
|
5.04% |
559.354 |
587.571 |
0.051 |
-0.02% |
0.051 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC64
|
5.03% |
567.368 |
595.924 |
0.016 |
0.06% |
0.016 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC127
|
5.03% |
1125.112 |
1181.728 |
0.026 |
-0.00% |
0.026 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC127
|
5.03% |
1125.146 |
1181.723 |
0.047 |
0.11% |
0.047 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC63
|
5.03% |
559.362 |
587.477 |
0.088 |
-0.56% |
0.088 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, Last>
|
4.99% |
14647.694 |
15377.892 |
5.457 |
-0.00% |
5.457 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<15, LessThanZero, Mid>
|
4.98% |
7814.325 |
8203.141 |
4.401 |
-0.02% |
4.401 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC128
|
4.93% |
1133.865 |
1189.757 |
0.025 |
-0.01% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC127
|
4.88% |
1126.775 |
1181.779 |
0.017 |
-0.16% |
0.017 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, LessThanZero, None>
|
4.88% |
15012.634 |
15744.518 |
7.401 |
2.37% |
7.401 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/28
|
4.82% |
59.325 |
62.182 |
0.001 |
3.56% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC3
|
4.80% |
27.437 |
28.754 |
0.002 |
0.92% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC7
|
4.75% |
15.010 |
15.724 |
0.000 |
46.64% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC8
|
4.65% |
70.591 |
73.877 |
0.002 |
0.33% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/44217
|
4.57% |
362.303 |
378.859 |
6.384 |
0.84% |
6.384 |
|
SingleSource/Benchmarks/Misc/salsa20
Profile
|
4.54% |
10.432 |
10.905 |
0.000 |
-0.66% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC8
|
4.48% |
70.565 |
73.724 |
0.025 |
-0.11% |
0.025 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_two_loads<uint64_t>/51
|
4.47% |
130.090 |
135.907 |
0.136 |
5.63% |
0.136 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC63
|
4.42% |
305.954 |
319.468 |
0.013 |
5.65% |
0.013 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC8
|
4.40% |
70.562 |
73.669 |
0.052 |
0.22% |
0.052 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, First>
|
4.34% |
8426.086 |
8791.578 |
11.527 |
4.24% |
11.527 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC16
|
4.33% |
146.345 |
152.684 |
0.002 |
0.08% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC16
|
4.33% |
146.347 |
152.682 |
0.003 |
0.09% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopFrom_uint16_t_To_uint32_t_
|
4.33% |
20562.511 |
21452.392 |
9.539 |
-0.00% |
9.539 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC16
|
4.32% |
146.347 |
152.673 |
0.004 |
0.02% |
0.004 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/1
|
4.11% |
190.476 |
198.302 |
1.287 |
-0.05% |
1.287 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC4
|
4.07% |
23.349 |
24.300 |
0.001 |
4.08% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC15
|
4.04% |
136.520 |
142.032 |
0.117 |
-2.10% |
0.117 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/1
|
3.99% |
191.749 |
199.404 |
0.880 |
0.06% |
0.880 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC15
|
3.97% |
75.620 |
78.623 |
0.001 |
3.94% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC3
|
3.86% |
27.419 |
28.476 |
0.053 |
0.09% |
0.053 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, Last>
|
3.85% |
38067.113 |
39531.737 |
27.317 |
-0.01% |
27.317 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Mid>
|
3.85% |
25375.430 |
26351.380 |
19.665 |
0.01% |
19.665 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopWithReductionTC16
|
3.84% |
80.531 |
83.625 |
0.001 |
3.70% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC3
|
3.79% |
27.420 |
28.459 |
0.035 |
-0.53% |
0.035 |
|
MultiSource/Benchmarks/mafft/pairlocalalign
Profile
|
3.74% |
46.174 |
47.903 |
0.009 |
0.74% |
0.009 |
|
MultiSource/Benchmarks/sim/sim
Profile
|
3.70% |
6.370 |
6.606 |
0.006 |
-1.54% |
0.006 |
|
MultiSource/Applications/siod/siod
Profile
|
3.70% |
5.474 |
5.676 |
0.009 |
3.92% |
0.009 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC32
|
3.70% |
282.861 |
293.323 |
0.003 |
0.11% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC32
|
3.63% |
282.936 |
293.212 |
0.035 |
0.06% |
0.035 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC32
|
3.60% |
282.849 |
293.033 |
0.012 |
0.00% |
0.012 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<2, LessThanZero, None>
|
3.45% |
42459.332 |
43922.884 |
31.783 |
-3.22% |
31.783 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, Last>
|
3.40% |
29277.583 |
30274.020 |
12.187 |
0.07% |
12.187 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, GreaterThanZero, Mid>
|
3.36% |
17569.976 |
18160.148 |
14.618 |
3.36% |
14.618 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, EqZero, Last>
|
3.34% |
29285.852 |
30262.696 |
24.558 |
3.36% |
24.558 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/51
|
3.33% |
21.443 |
22.157 |
0.000 |
3.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/28
|
3.33% |
21.443 |
22.157 |
0.000 |
3.32% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/16
|
3.33% |
21.443 |
22.157 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_VOL3D_CALC_LAMBDA/2
|
3.33% |
7.514 |
7.764 |
0.001 |
-0.02% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/10
|
3.33% |
21.443 |
22.157 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/256
|
3.32% |
21.443 |
22.156 |
0.001 |
3.32% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint32_t>/999
|
3.32% |
21.444 |
22.156 |
0.000 |
3.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/28
|
3.23% |
22.157 |
22.872 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/999
|
3.22% |
22.157 |
22.872 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/51
|
3.22% |
22.157 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/16
|
3.22% |
22.158 |
22.871 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/10
|
3.22% |
22.157 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/10
|
3.22% |
22.158 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/28
|
3.22% |
22.157 |
22.871 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/256
|
3.22% |
22.157 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/999
|
3.22% |
22.157 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/51
|
3.22% |
22.157 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, Mid>
|
3.22% |
22705.274 |
23436.289 |
1.316 |
3.25% |
1.316 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/256
|
3.22% |
22.157 |
22.870 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/51
|
3.22% |
22.158 |
22.871 |
0.001 |
3.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/28
|
3.22% |
22.157 |
22.871 |
0.000 |
3.21% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/10
|
3.22% |
22.157 |
22.870 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint16_t>/16
|
3.22% |
22.158 |
22.871 |
0.001 |
3.22% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/16
|
3.22% |
22.157 |
22.870 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_two_loads<uint8_t>/256
|
3.22% |
22.158 |
22.871 |
0.001 |
0.00% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<3, LessThanZero, None>
|
3.22% |
30253.598 |
31226.812 |
22.610 |
-0.00% |
22.610 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_first_three_loads<uint32_t>/999
|
3.22% |
22.158 |
22.871 |
0.001 |
-0.01% |
0.001 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, Mid>
|
3.15% |
13390.558 |
13812.332 |
7.229 |
3.15% |
7.229 |
|
MultiSource/Benchmarks/PAQ8p/paq8p
Profile
|
3.10% |
131.665 |
135.747 |
0.041 |
3.25% |
0.041 |
|
MicroBenchmarks/ImageProcessing/Blur/blur.test:BENCHMARK_GAUSSIAN_BLUR/1024
|
3.05% |
253966.333 |
261704.667 |
2.514 |
0.01% |
2.514 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, LessThanZero, None>
|
3.03% |
24160.489 |
24893.208 |
15.906 |
0.01% |
15.906 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, EqZero, Last>
|
2.96% |
19912.632 |
20502.460 |
11.116 |
2.96% |
11.116 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<8, GreaterThanZero, Mid>
|
2.94% |
12450.722 |
12816.349 |
7.943 |
2.93% |
7.943 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<32, EqZero, Mid>
|
2.91% |
3119.774 |
3210.647 |
0.904 |
2.90% |
0.904 |
|
MultiSource/Benchmarks/Fhourstones/fhourstones
Profile
|
2.91% |
2.317 |
2.384 |
0.014 |
2.97% |
0.014 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<5, LessThanZero, Last>
|
2.85% |
20496.633 |
21081.255 |
18.551 |
2.81% |
18.551 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, GreaterThanZero, Last>
|
2.71% |
17567.983 |
18044.302 |
7.564 |
2.77% |
7.564 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<6, LessThanZero, None>
|
2.66% |
18051.885 |
18531.371 |
11.278 |
-0.00% |
11.278 |
|
MultiSource/Applications/aha/aha
Profile
|
2.65% |
3.775 |
3.875 |
0.001 |
-0.44% |
0.001 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_PRESSURE_CALC_RAW/171
|
2.65% |
1.322 |
1.357 |
0.000 |
9.57% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetALambdaLoops/lcalsALambda.test:BM_DEL_DOT_VEC_2D_LAMBDA/2
|
2.65% |
2.346 |
2.408 |
0.019 |
2.68% |
0.019 |
|
MicroBenchmarks/Builtins/Int128/Builtins.test:BM_DivideIntrinsic128UniformDivisor<__uint128_t>
|
2.64% |
37.508 |
38.500 |
0.033 |
3.03% |
0.033 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC2
|
2.64% |
20.006 |
20.534 |
0.010 |
-1.43% |
0.010 |
|
MicroBenchmarks/LoopVectorization/LoopEpilogueVectorizationBenchmarks.test:benchReductionAutoVec<uint8_t>/127
|
2.59% |
167.206 |
171.534 |
0.541 |
0.82% |
0.541 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<7, EqZero, None>
|
2.56% |
16314.937 |
16732.734 |
10.629 |
2.56% |
10.629 |
|
SingleSource/Benchmarks/Misc/revertBits
Profile
|
2.56% |
0.401 |
0.411 |
0.000 |
-0.01% |
0.000 |
|
External/SPEC/CINT2017rate/500.perlbench_r/500.perlbench_r
Profile
|
2.53% |
100.844 |
103.399 |
0.120 |
2.26% |
0.120 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_single_load<uint64_t>/10
|
2.50% |
28.590 |
29.303 |
0.001 |
-0.01% |
0.001 |
|
MultiSource/Benchmarks/nbench/nbench
Profile
|
2.34% |
3.782 |
3.870 |
0.003 |
2.37% |
0.003 |
|
MultiSource/Applications/hexxagon/hexxagon
Profile
|
2.33% |
9.020 |
9.231 |
0.002 |
-3.66% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint32_t>/51
|
2.31% |
92.207 |
94.341 |
0.003 |
0.75% |
0.003 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW4BigLoopTC2
|
2.30% |
20.009 |
20.470 |
0.015 |
-0.81% |
0.015 |
|
MultiSource/Benchmarks/DOE-ProxyApps-C++/miniFE/miniFE
Profile
|
2.23% |
22.398 |
22.898 |
0.082 |
-0.11% |
0.082 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC128
|
2.22% |
157.933 |
161.446 |
0.453 |
5.01% |
0.453 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC8
|
2.22% |
10.721 |
10.959 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC8
|
2.22% |
10.721 |
10.960 |
0.000 |
-4.17% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC8
|
2.22% |
10.721 |
10.959 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_two_loads<uint32_t>/10
|
2.21% |
32.165 |
32.877 |
0.001 |
2.21% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1BigLoopWithReductionTC64
|
2.17% |
305.613 |
312.246 |
0.254 |
1.64% |
0.254 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4BigLoopTC2
|
2.14% |
20.048 |
20.477 |
0.014 |
-0.70% |
0.014 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/10
|
2.12% |
33.593 |
34.306 |
0.001 |
-0.00% |
0.001 |
|
SingleSource/Benchmarks/Stanford/FloatMM
Profile
|
2.04% |
0.753 |
0.769 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/10
|
1.95% |
36.454 |
37.166 |
0.001 |
1.92% |
0.001 |
|
SingleSource/Benchmarks/Adobe-C++/functionobjects
Profile
|
1.90% |
5.950 |
6.063 |
0.002 |
-0.01% |
0.002 |
|
MultiSource/Benchmarks/MiBench/telecomm-CRC32/telecomm-CRC32
Profile
|
1.84% |
0.586 |
0.597 |
0.002 |
-0.37% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4BigLoopTC1
|
1.82% |
12.564 |
12.792 |
0.003 |
-0.63% |
0.003 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, LessThanZero, None>
|
1.81% |
5174.406 |
5268.222 |
2.012 |
0.03% |
2.012 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC128
|
1.81% |
157.945 |
160.805 |
0.005 |
3.44% |
0.005 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/16
|
1.69% |
42.170 |
42.883 |
0.001 |
-0.00% |
0.001 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_asinf_autovec_float_
|
1.67% |
385.385 |
391.824 |
0.264 |
1.65% |
0.264 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_early_exit_taken_mid_three_loads<uint16_t>/16
|
1.66% |
42.886 |
43.598 |
0.000 |
-3.17% |
0.000 |
|
MicroBenchmarks/LCALS/SubsetARawLoops/lcalsARaw.test:BM_DEL_DOT_VEC_2D_RAW/0
|
1.63% |
1202.311 |
1221.866 |
1.207 |
0.15% |
1.207 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:BENCHMARK_expf_novec_float_
|
1.60% |
456.037 |
463.330 |
0.071 |
1.66% |
0.071 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint16_t>/10
|
1.51% |
47.175 |
47.888 |
0.000 |
-0.01% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/10
|
1.47% |
48.603 |
49.316 |
0.002 |
4.54% |
0.002 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForLoopWithReductionAutoVecTC31
|
1.45% |
49.318 |
50.031 |
0.001 |
52.16% |
0.001 |
|
MultiSource/Applications/SPASS/SPASS
Profile
|
1.40% |
25.713 |
26.073 |
0.065 |
2.14% |
0.065 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:benchForTruncOrZextVecWithAddInLoopWithVW8From_uint16_t_To_uint64_t_
|
1.38% |
21896.783 |
22199.772 |
1.704 |
-0.01% |
1.704 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW4LoopWithReductionTC15
|
1.37% |
17.393 |
17.630 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC4VW1LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
-33.33% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC2VW1LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
-0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW1LoopWithReductionTC15
|
1.37% |
17.393 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/LoopVectorization/LoopInterleavingBenchmarks.test:benchForIC1VW4LoopWithReductionTC15
|
1.37% |
17.392 |
17.630 |
0.000 |
0.00% |
0.000 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, None>
|
1.35% |
5187.396 |
5257.455 |
2.374 |
1.34% |
2.374 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<4, EqZero, Mid>
|
1.32% |
8334.359 |
8444.065 |
0.321 |
0.04% |
0.321 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/16
|
1.29% |
119.067 |
120.606 |
0.002 |
0.03% |
0.002 |
|
External/SPEC/CFP2017rate/544.nab_r/544.nab_r
Profile
|
1.28% |
276.616 |
280.156 |
0.082 |
-0.01% |
0.082 |
|
External/SPEC/CINT2017rate/531.deepsjeng_r/531.deepsjeng_r
Profile
|
1.23% |
136.894 |
138.574 |
0.098 |
0.83% |
0.098 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_single_load<uint8_t>/28
|
1.20% |
59.326 |
60.036 |
0.002 |
-0.00% |
0.002 |
|
MicroBenchmarks/LCALS/SubsetCRawLoops/lcalsCRaw.test:BM_INT_PREDICT_RAW/171
|
1.17% |
2.067 |
2.092 |
0.001 |
-0.01% |
0.001 |
|
SingleSource/Benchmarks/Misc/ReedSolomon
Profile
|
1.17% |
9.522 |
9.633 |
0.002 |
0.75% |
0.002 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<63, GreaterThanZero, None>
|
1.14% |
3023.337 |
3057.698 |
0.366 |
1.15% |
0.366 |
|
MicroBenchmarks/MemFunctions/MemFunctions.test:BM_MemCmp<31, GreaterThanZero, Mid>
|
1.11% |
4954.208 |
5009.226 |
1.371 |
1.15% |
1.371 |
|
External/SPEC/CINT2017rate/523.xalancbmk_r/523.xalancbmk_r
Profile
|
1.10% |
211.461 |
213.795 |
0.844 |
0.09% |
0.844 |
|
MicroBenchmarks/LoopVectorization/LoopVectorizationBenchmarks.test:autovec_no_early_exit_three_loads<uint64_t>/16
|
1.08% |
65.757 |
66.467 |
0.002 |
6.89% |
0.002 |
|
MicroBenchmarks/ImageProcessing/Interpolation/Interpolation.test:BENCHMARK_BICUBIC_INTERPOLATION/64
|
1.01% |
2623.685 |
2650.125 |
0.056 |
0.00% |
0.056 |